We offer numerous technologies for license that can be combined and applied across a broad range of technical fields and industries. Following is just a small sample of how companies have licensed SRI’s speech and natural language technologies. Contact us through the form below to learn about strategic licensing opportunities.
Speech and Natural Language
Anyone who recognizes the voice of a loved one knows the human voice is a powerful tool. Speech and language technologies not only allow us to interact naturally with a variety of computing applications—they also provide a wealth of information about our intentions, health and emotional state.
SRI's Speech Technology and Research (STAR) Laboratory is home to multidisciplinary teams of expert engineers, computer scientists and linguists who work with you to build and customize systems that meet your needs. Our teams have created software applications for a wide range of applications including signal processing, mathematical modeling, acoustics, data indexing and mining, and computer-aided learning. Core areas of research and development include:
- Speech recognition
- Speech-to-speech translation
- Natural language understanding
- Human/computer dialog systems
- Machine translation
- Information extraction
- Speaker state analysis
- Speaker/audio characterization
- Voice biometrics/speaker identification
- Accurate recognition in noisy environments
Featured Speech and Natural Language Solutions
SRI Language Modeling Toolkit
The SRI Language Modeling (SRILM) toolkit offers tools for building and applying statistical language models for use in speech recognition, statistical tagging and segmentation, and machine translation. The toolkit can be downloaded and used free of charge.
EduSpeak® Speech Recognition Toolkit
EduSpeak is a speech recognition toolkit specifically designed for developers of language-learning applications and other educational and training software. EduSpeak works for both adult and child voices, and it excels at recognizing both native and non-native speakers.
DynaSpeak® Speech Recognition Engine
DynaSpeak is a small-footprint, high-accuracy speech recognition engine. It incorporates patented techniques that increase recognition performance using speaker adaptation, microphone adaptation, end-of- speech detection, distributed speech recognition and noise robustness.